George A.K. van Voorn

The paper develops a hierarchical Bayesian model to analyze dynamic phenotypes in multi-environment trials, quantifying genotype, environment, and G x E effects on growth parameters.

The paper develops a Physics-Informed Neural Network (PINN) for predicting plant height growth, showing improved accuracy over traditional models with limited data.

The paper examines model-based strategies for mitigating cyanobacterial blooms in lakes with alternative stable states, evaluating their effectiveness and costs.